StatFest: Stats Central making sense of noise since 2016
Description
To celebrate 10 years of Stats Central you are invited to a day on which UNSW students and researchers can access all of our services for free. The program includes a public lecture by DVC Academic Quality Professor Merlin Crossley and a series of practical sessions designed to build skills in study design, data analysis, and bioinformatics.
Seminars will cover topics from causal inference and mixed models to meta-analysis and data visualisation. StatFest offers something for anyone looking to strengthen their statistical skills. Sessions are designed to be accessible and applicable to real research problems.
Free Tickets - refreshments & lunch
Date: 22 May 2026
Time: 9.45am-5pm
Location: Colombo House
RSVP: by 18 May 2026
Public Lecture (Professor Merlin Crossley)
From blobs to numbers: the digital revolution in biology at UNSW
Time: 4 pm
Location: Colombo Theatre A
When Leeuwenhoek looked down the first microscope in the 17th century, he essentially
saw blobs. When Darwin looked out from the Beagle in the 19th century, he saw blobs too.
But when Max Perutz solved the high-resolution structure of haemoglobin in the middle of
the last century, he was seeing atoms. Watson and Crick also showed atoms in their
structure of DNA in 1953. Biology had become chemistry, and the age of molecular biology
began.
Now the genomes of thousands of organisms have been sequenced, and the structures of
thousands of proteins. It is possible to deduce the structures of proteins using AI. AlphaFold
won the Nobel Prize for Chemistry in 2024. But this isn’t really chemistry now – it’s
mathematics, statistics, and computation.
Biology has now become mathematics and data science. But most biologists were not drawn
into the field by their love of numbers.
Happily, UNSW has always been a place that has loved numbers. We have Australia’s largest
Engineering Faculty, and it is supported by other excellent Schools, including Mathematics &
Statistics and Computer Science & Engineering. But beyond organisational operations
individual researcher and student support is necessary, and the Stats Central was an
inspired and essential initiative. UNSW is well placed as the age of digital biology and
precision medicine unfolds.
Professor Merlin Crossley AM is Deputy Vice-Chancellor (Academic Quality) at UNSW Sydney and a Professor of Molecular Biology. His research has focused on gene regulation and the molecular mechanisms underlying diseases such as thalassaemia. He is an enthusiastic science communicator, and amongst other contributions, is Chair of the Editorial Boards of The Conversation and UNSW Press. He was a Rhodes Scholar, a recipient of the NSW Premier’s Award for Medical Biological Science, and in 2021 a species of iridescent squid was named in his honour – Iridoteuthis merlini – Merlin’s butterfly bobtail squid!
Short Course: Bulk RNA-seq Analysis Using nf-core Workflows on Katana
Time: 10 am - 3:30 pm
This workshop introduces the key concepts and practical workflows for analysing bulk RNA-seq data using nf-core pipelines on UNSW's Katana high-performance computing system. Participants will learn how to run best practice nf-core RNA-seq analysis workflows, assess sequencing and mapping quality, interpret QC reports, and perform downstream differential gene expression analysis.
The course combines short conceptual explanations with hands-on practice. Topics include:
Introduction to bulk RNA-seq
Introduction to Nextflow and nf-core workflows
Quality assessment using FastQC
Post-alignment RNA-seq QC using RSeQC
Read mapping and sample-level QC
differential gene expression analysis.
Pre-requisites
Basic familiarity with Linux command-line usage and access to Katana are required. No advanced programming experience is expected, but participants should be comfortable navigating folders, running shell commands, and editing simple text files.
Seminar Schedule
- 10:00 am - 11:30 am
Practical Study Design
The aim of this talk is to provide you with tools to improve your study design. Expect to learn: What confounding actually means; Measured and unmeasured confounding in observational studies and how to best address it; Natural experiments, manipulative experiments and randomised controlled trials; Power calculations; How to conduct randomisation, and much more!
- 11:30 am - 12:15 am
A primer on causal inference
This talk is a short introduction to the field of statistics known as causal inference: the design and analysis of experiments and observational studies to answer causal questions. How do we go beyond association and estimate causal effects? I will introduce the potential outcomes framework as a way of structuring causal thinking. In the context of observational studies, I will discuss matching as one method of reducing confounding. The talk also provides some illustrative examples of causal inference methods in practice.
- 1:30 pm - 2:15 pm
Trust or Confidence: Using Confidence Intervals
Despite the American Statistical Association releasing a statement 10 years ago saying that "Scientific conclusions and business or policy decisions should not be based only on whether a p-value passes a specific threshold", in practice, still some conclusions and decisions are being based on a single value (usually a significance level of 0.05). The talk will cover the importance of confidence intervals in making conclusions, rather than relying only on p-values.
- 2:15 pm - 3:00 pm
A Practical Guide to Meta-Analysis
Meta-analysis is a commonly used method to combine results across studies, but how does it work in practice? This seminar provides a practical introduction to meta-analysis. Key concepts that will be covered include types of effect size measures, the difference between fixed and random effects models, meta-regression, as well as concepts of heterogeneity and publication bias. Concepts are illustrated using examples in R.
- 3:00 pm - 3:45 pm
Transforming Data into Insights: Principles for Effective Data Visualisation
We often ask clients and collaborators to visualise their data and, at times, their statistical outputs. But how do we do this in a way that everyone involved is satisfied with the visualisations? This talk will describe general principles of visualisation from a statistician’s viewpoint, then explore a variety of plots from the wild and evaluate them against these guidelines. I will finish by showing how these principles can be “bent” to tell the story that your data (and your statistical outputs) has to share.
Tickets for good, not greed Humanitix dedicates 100% of profits from booking fees to charity
